Released: 2026-06-18

Qwen3-235B

Alibaba 235B open-weight Mixture-of-Experts foundation model supporting dual thinking/non-thinking inference modes.

Intelligence Index
91.5/ 100
Calibrated multi-domain composite
Throughput Speed
70tok/sec
Output streaming throughput
Time To First Token
410ms
Initial chunk server latency
LiveBench Contam-Free
77.4%
September 2026 suite score

LiveBench Multi-Domain Evaluation Breakdown

Monthly refreshed contamination-free test sets
Logical Reasoning87.5%
Coding & Repo Repair80.5%
Mathematics (AIME)91.0%
Data Analysis & Tables74.8%
Language & Comprehension70.5%
Instruction Following64.0%

Sourced Benchmark Evaluations (3)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
ARC-AGI-2Nearing Saturation71.4%
75
2026-07-16independentSource ↗
SWE-bench VerifiedSaturated61.2%
25
2026-06-27independentSource ↗
IFEvalDeprecated64%
25
2026-06-22independentSource ↗
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run qwen3-235b

# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-235b",
    "messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
  }'

Evaluation & Sourcing Notes

Scores listed for Qwen3-235B represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.